leadership and motivation in hospitality

Step Diagnostic observations and actions (Model 4)

1

The usual indicators + WV2 load low on their factors

For the usual substantive reasons, JP4 is retained, though loading only 0.489

ML4 ML5 JP3 ME5 ME7 JS2 JS3 JS4 WV2 are all removed

2

No major loading issues. Flagged for observation are WV3 at 0.654, JS5 at

0.677 and DSB3 at 0.669

Standardised residual covariance matrix (SRCM) highlights high levels of

unmeasured variance between DSB3/JP4 DSB4/JP4 and JS5/ML3

DSB3, DSB4 and JS5 removed

3

All SRCs are under 2.58

Modification indices highlight AOC2/AOC4 as the largest MI; there is item

content overlap (as described in Model 3); AOC2/4 loadings are similar; AOC4

has greater associated unmeasured variance in the SRCM than (12.7 versus

8.7 for AOC2)

AOC4 removed

4

All SRCs are under 2.58

Modification indices (MIs) highlight WV4/WV7; there is no obvious item

overlap and no statistical means of identifying one as being weaker (i.e. as a

better choice for removal)

Next pairing highlighted by MIs is JS1/JS6; JS6 overlaps with ME1 (as per

model 3) - JS6 removed

Also highlighted by the MIs is AOC1/AOC2; these have item content overlap

(as per Model 3) and the SRCM shows that AOC1 has much higher levels of

unmeasured variance – AOC1 removed

5

All SRCs are under 2.58

MIs highlight WV7/WV4 and WV3/WV4 for inspection; no item overlap leads to

an examination of the SRCM

WV7 has greatest unmeasured variance (7 = 17.6; 4 = 10.8; 3 = 14.2)

WV7 removed

6

All SRCs are under 2.58
MIs highlight WV3/WV4 and WV3/WV6 for inspection
No item overlap but WV3 significantly weaker on loading values
WV3 removed
7 Good fit

Table 7-22 Modification steps for CFA 4:1 to 4:7

The removal of WV2 (Working, in general... Provides me with an income that is
needed) and WV3 (...Helps keep me busy/occupied) was anticipated - Section 5.1
describes how these items are semantically somewhat different from the other
WV statements. The removal of WV7 (...Is one of the most important things in
my life) was also not surprising since this item did not belong to the original set of
statements in the MOW (1995) survey form. None of these item removals has a
significant impact on the substantive content of the WV construct, which – based
on the remaining indicators WV1, WV4 and WV5^16 - continues to be defined as “an
16
WV1 = Working, in general... Gives me status and prestige (gives me a feeling of being
worthwhile)
WV4 = ...Lets me meet interesting people
WV5 = ...Is a useful way for me to contribute to society