Scotland's People: Volume 6 : Technical Report

4. Response rates, achieved sample profile and weighting

4.1 Achieved sample size

The nature of the SHS as a survey with continuous fieldwork means that separating the data into fieldwork periods and data files for analysis involves simply establishing cut-off dates and any data submitted to the CAPI servers by a particular date is assigned to one data period or another. In each dataset there are a few interviews that, strictly speaking, belong to a different data period. For example, in the 2001 data 74 of the 15,566 interviews were carried out on the sample issued in 2000. Similarly, there are 93 interviews carried out on the 2001 sample that were not on the CAPI servers when the 2001 data file was closed. These interviews are carried into the file for 2002.

When calculating response rates based on the sample issued in 2001, we need to exclude the 74 interviews from the previous sample and include the 93 interviews that will be in the 2002 data. There is, therefore, a difference of 19 interviews between the records in the 2001 data file and the number of interviews achieved on 2001 sample, as shown below.

Interviews in 2001 data file	15,566
minus 74 carried out on 2000 sample	15,492
plus 93 carried into 2002 data	15,585 interviews on 2001 sample
net difference	+19 interviews

As Table 4-1 shows, these were spread quite evenly across the four quarters covered by the survey within local authorities. On a month-on-month basis, the variation is greater. There are likely to be a variety of reasons for this fluctuation, including the unavailability of interviewers and potential respondents because of sickness or holidays, periods of bad weather which disrupt fieldwork, and slight variations in the fieldwork allocation by month within individual local authority areas.

Table 4-1

Achieved interviews by local authority area by month in which sample was issued, SHS 2001

(based on month of issue, not date of interview)

	Jan	Feb	Mar	Q1 total	Apr	May	Jun	Q2 total	Jul	Aug	Sep	Q3 total	Oct	Nov	Dec	Q3 total	Total
Aberdeen City	62	50	48	160	61	56	45	162	52	53	50	155	60	65	58	183	660
Aberdeenshire	63	42	47	152	49	60	41	150	51	57	41	149	58	52	47	157	608
Angus	27	37	23	87	41	30	14	85	26	22	31	79	24	24	27	75	326
Argyll and Bute	25	32	31	88	17	9	37	63	23	21	27	71	29	27	26	82	304
Borders	35	22	18	75	25	31	23	79	21	37	27	85	31	37	21	89	328
Clackmannanshire	27	30	19	76	37	16	21	74	32	17	21	70	24	19	20	63	283
Dumfries and Galloway	34	46	41	121	31	24	32	87	36	33	33	102	31	31	48	110	420
Dundee City	42	34	46	122	28	35	35	98	36	44	32	112	43	25	26	94	426
East Ayrshire	47	22	32	101	29	41	36	106	31	37	40	108	36	11	19	66	381
East Dunbartonshire	26	26	25	77	26	27	21	74	26	25	20	71	22	41	20	83	305
East Lothian	23	27	19	69	34	20	13	67	33	23	20	76	19	33	18	70	282
East Renfrewshire	21	15	24	60	24	22	25	71	33	26	19	78	24	25	22	71	280
Edinburgh, City of	122	119	115	356	103	124	118	345	88	86	103	277	98	90	86	274	1,252
Eilean Siar	24	22	28	74	44	26	31	101	38	26	25	89	28	29	29	86	350
Falkirk	35	32	35	102	32	37	22	91	30	37	36	103	35	31	35	101	397
Fife	86	88	66	240	72	77	80	229	68	77	70	215	72	75	88	235	919
Glasgow City	171	175	169	515	171	121	132	424	137	117	123	377	132	110	133	375	1,691
Highland	68	43	63	174	46	54	47	147	43	59	52	154	50	39	42	131	606
Inverclyde	25	24	27	76	23	32	25	80	23	24	26	73	19	18	25	62	291
Midlothian	33	17	29	79	38	25	25	88	31	22	24	77	24	21	23	68	312
Moray	24	40	24	88	27	24	27	78	22	19	31	72	22	24	35	81	319
North Ayrshire	36	34	36	106	37	37	36	110	32	31	23	86	34	34	39	107	409
North Lanarkshire	89	67	87	243	63	72	78	213	66	83	58	207	73	53	66	192	855
Orkney	27	25	20	72	23	18	22	63	37	21	24	82	16	30	18	64	281
Perth and Kinross	26	39	32	97	42	31	30	103	18	25	37	80	33	24	25	82	362
Renfrewshire	49	43	46	138	34	38	44	116	33	31	42	106	41	44	40	125	485
Shetland	43	28	17	88	23	24	13	60	23	23	24	70	23	33	24	80	298
South Ayrshire	32	40	25	97	38	23	19	80	31	21	35	87	29	17	37	83	347
South Lanarkshire	76	75	77	228	78	60	92	230	71	60	63	194	49	61	48	158	810
Stirling	26	22	21	69	12	33	18	63	29	37	24	90	40	27	13	80	302
West Dunbartonshire	34	25	22	81	27	21	25	73	24	36	23	83	17	13	19	49	286
West Lothian	58	33	35	126	45	25	32	102	35	28	31	94	27	39	22	88	410
Total	1,516	1,374	1,347	4,237	1,380	1,273	1,259	3,912	1,279	1,258	1,235	3,772	1,263	1,202	1,199	3,664	15,585

In addition to these interviews, a small number of sampled address remain valid for reissue and will be incorporated in the reissue programme in 2002, which might further increase the number of interviews and the response rate.

4.2 Household response rate

Table 4.2 shows the detailed outcomes of issued addresses for the 2001 SHS as a whole. Across the year, 92% of issued addresses were valid and at least a 'highest income householder' interview was achieved at 67% of those addresses. Although the target number of interviews from 2001 was exceeded, the response rate is below the target of 70%. This reflects three factors:

the proportion of invalid addresses is slightly lower than the projected 10% used to sample addresses. This tends to reduce the response rate
some addresses remain in the field as re-issues from previous waves of fieldwork. These are counted as valid addresses for now but when these are closed, some of them will be invalid, which will increase the response rate slightly
about 3% of addresses appear to interviewers to be unoccupied but this has not been confirmed by neighbours so these addresses as counted as valid address, which again tends to depress the response rate.

Table 4-2

Summary of outcomes at issued addresses for the 2001 SHS

Valid addresses	Frequency	Percent of issued addresses	Percent of sub-category
Interview achieved	15,585	61.9	67.2
Refused - not interested	1,845	7.3	8.0
Refused - too busy	855	3.4	3.7
Refused - too ill	440	1.7	1.9
Refused -- never does surveys	231	0.9	1.0
Proxy refusal	14	0.1	0.1
No contact - address occupied	1,659	6.6	7.2
No contact - questionable if occupied	685	2.7	3.0
No contact - away during fieldwork	375	1.5	1.6
Contact but inadequate English	18	0.1	0.1
No contact after five calls	191	0.8	0.8
Other non-contact	527	2.1	2.3
Valid address still in field	772	3.1	3.3
Total	23,197	92.1	100.0
Invalid addresses
Vacant	1,009	4.0	50.5
Institution	45	0.2	2.3
No longer dwelling	37	0.1	1.9
Business	312	1.2	15.6
Derelict/demolished	237	0.9	11.9
No trace	187	0.7	9.4
Other invalid	172	0.7	8.6
Total invalid addresses	1,999	7.9	100.0
Total addresses issued	25,196	100.0

Examination of overall household response rates by local authority area reveals considerable variation both in the level of 'deadwood' in the sample and in the achieved response rate. The combined effects of these mean that the original projections of annual sub-sample size have been surpassed in some local authority areas but not reached in others. Fieldwork in 2001 saw a general improvement in the response rates for the survey, with almost all areas recording an increase. The response rate is highest in Eilean Siar (88%) and Argyll and Bute (76%) and lowest in Edinburgh (62%) and Fife (62%). Table 4.3 shows this in detail.

Table 4-3

Household response rate, targets and invalid addresses by local authority: 2001

Change in response rates between 1999/2000 and 2001

	Target	Achieved	% of target achieved	Response rate 2001	Response rate 1999/2000	Change since 1999/2000	Percentage of addressesinvalid
Aberdeen City	648	660	102%	68.1	64.6	3.5	7.7
Aberdeenshire	594	608	102%	68.1	68.0	0.1	7.7
Angus	308	326	106%	71.3	66.6	4.7	8.0
Argyll and Bute	297	304	102%	76.4	70.9	5.5	16.0
Borders	303	328	108%	72.1	68.4	3.7	8.8
Clackmannanshire	292	283	97%	64.8	65.8	-1.0	6.2
Dumfries and Galloway	418	420	100%	68.1	69.2	-1.1	8.0
Dundee City	450	426	95%	64.1	62.4	1.7	9.4
East Ayrshire	336	381	114%	71.9	68.5	3.4	4.5
East Dunbartonshire	276	305	111%	69.3	67.8	1.5	1.8
East Lothian	297	282	95%	62.7	67.2	-4.5	5.9
East Renfrewshire	276	280	101%	65.7	58.9	6.8	5.1
Edinburgh, City of	1,320	1252	95%	62.0	64.2	-2.2	6.0
Eilean Siar	286	350	122%	88.2	78.8	9.4	14.8
Falkirk	396	397	100%	64.9	65.7	-0.8	4.5
Fife	974	919	94%	61.9	64.5	-2.6	5.7
Glasgow City	1,806	1691	94%	65.2	61.5	3.7	11.3
Highland	583	606	104%	71.0	67.7	3.3	9.5
Inverclyde	276	291	105%	72.8	68.1	4.6	10.3
Midlothian	297	312	105%	66.8	66.2	0.6	4.5
Moray	297	319	107%	73.8	72.3	1.5	9.4
North Ayrshire	391	409	105%	68.1	70.4	-2.3	6.5
North Lanarkshire	864	855	99%	66.9	61.1	5.8	7.7
Orkney	281	281	100%	67.5	69.8	-2.3	10.5
Perth and Kinross	369	362	98%	66.8	69.5	-2.7	8.1
Renfrewshire	504	485	96%	67.4	64.3	3.1	11.9
Shetland	281	298	106%	71.5	69.8	1.7	9.3
South Ayrshire	319	347	109%	70.0	67.4	2.6	4.1
South Lanarkshire	820	810	99%	65.2	63.7	1.5	6.0
Stirling	297	302	102%	70.1	68.2	1.9	8.5
West Dunbartonshire	276	286	101%	68.8	62.9	5.9	8.0
West Lothian	413	410	99%	63.8	64.5	-0.7	5.2
All Scotland	15,540	15,578	100%	67.2	65.7	1.5	7.9

In 2001 the worst performance was in Fife and Glasgow, both of which have achieved 94% of target. This is an improvement on 1999/2000 where the worst performance for achieving interviews against target was in Glasgow and Dundee, both of which stood at 87% of target when we last reported. The best performance continues to be in Eilean Siar with interviews 22% over target and a response rate of 88% of valid addresses.

Page updated: Friday, April 07, 2006

Scottish Government